tokens, tokenizer, and vocab

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "processor_class": "Wav2Vec2Processor",
+  "replace_word_delimiter_char": " ",
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,48 @@
+{
+  "'": 6,
+  "1": 7,
+  "2": 23,
+  "5": 29,
+  "8": 31,
+  "9": 34,
+  "[PAD]": 45,
+  "[UNK]": 44,
+  "a": 8,
+  "b": 32,
+  "c": 16,
+  "d": 11,
+  "e": 18,
+  "f": 19,
+  "g": 22,
+  "h": 12,
+  "i": 5,
+  "j": 4,
+  "k": 10,
+  "l": 38,
+  "m": 25,
+  "n": 26,
+  "o": 9,
+  "p": 17,
+  "q": 43,
+  "r": 33,
+  "s": 35,
+  "t": 15,
+  "u": 1,
+  "v": 40,
+  "w": 28,
+  "x": 30,
+  "y": 0,
+  "z": 42,
+  "|": 20,
+  "´": 13,
+  "à": 41,
+  "á": 14,
+  "é": 36,
+  "ì": 2,
+  "í": 3,
+  "ñ": 24,
+  "ò": 37,
+  "ó": 39,
+  "ú": 21,
+  "ü": 27
+}